Lucene学习之Facet

Facet简单来说就是点击某个品牌或者网络，获取更细分的结果。也就是站在不同的方面去搜索会得到不同的结果，其主要API支持，我们通过一段代码来看

import java.io.IOException;
import java.util.ArrayList;
import java.util.List;

import org.apache.lucene.analysis.core.WhitespaceAnalyzer;
import org.apache.lucene.document.Document;
import org.apache.lucene.facet.DrillDownQuery;
import org.apache.lucene.facet.DrillSideways;
import org.apache.lucene.facet.FacetField;
import org.apache.lucene.facet.FacetResult;
import org.apache.lucene.facet.Facets;
import org.apache.lucene.facet.FacetsCollector;
import org.apache.lucene.facet.FacetsConfig;
import org.apache.lucene.facet.taxonomy.FastTaxonomyFacetCounts;
import org.apache.lucene.facet.taxonomy.TaxonomyReader;
import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyReader;
import org.apache.lucene.facet.taxonomy.directory.DirectoryTaxonomyWriter;
import org.apache.lucene.index.DirectoryReader;
import org.apache.lucene.index.IndexWriter;
import org.apache.lucene.index.IndexWriterConfig;
import org.apache.lucene.search.IndexSearcher;
import org.apache.lucene.search.MatchAllDocsQuery;
import org.apache.lucene.store.Directory;
import org.apache.lucene.store.RAMDirectory;


public class SimpleFacetsExample {
    private final Directory indexDir = new RAMDirectory();
    private final Directory taxoDir = new RAMDirectory();
    private final FacetsConfig config = new FacetsConfig();

    public SimpleFacetsExample(){
        //设置多值域
        this.config.setHierarchical("Author", true);
        this.config.setHierarchical("Publish Date", true);
    }

    private void index() throws IOException{
        IndexWriter indexWriter = new IndexWriter(this.indexDir,
                new IndexWriterConfig(
                        new WhitespaceAnalyzer()).setOpenMode
                        (IndexWriterConfig.OpenMode.CREATE));//create a new index
        DirectoryTaxonomyWriter taxoWriter = new DirectoryTaxonomyWriter(this.taxoDir);
        Document doc = new Document();
        doc.add(new FacetField("Author",new String[]{"Bob"}));
        doc.add(new FacetField("Publish Date",new String[]{"2010","10","15"}));
        indexWriter.addDocument(this.config.build(taxoWriter, doc));

        doc = new Document();
        doc.add(new FacetField("Author",new String[]{"Lisa"}));
        doc.add(new FacetField("Publish Date",new String[]{"2010","10","20"}));
        indexWriter.addDocument(this.config.build(taxoWriter,doc));

        doc = new Document();
        doc.add(new FacetField("Author",new String[]{"Lisa"}));
        doc.add(new FacetField("Publish Date",new String[]{"2012","1","1"}));
        indexWriter.addDocument(this.config.build(taxoWriter,doc));

        doc = new Document();
        doc.add(new FacetField("Author",new String[]{"Susan"}));
        doc.add(new FacetField("Publish Date",new String[]{"2012","1","7"}));
        indexWriter.addDocument(this.config.build(taxoWriter,doc));

        doc = new Document();
        doc.add(new FacetField("Author",new String[]{"Frank"}));
        doc.add(new FacetField("Publish Date",new String[]{"1999","5","5"}));
        indexWriter.addDocument(this.config.build(taxoWriter,doc));

        indexWriter.close();
        taxoWriter.close();
    }

        private List<FacetResult> facetsWithSearch() throws IOException{
            DirectoryReader indexReader = DirectoryReader.open(this.indexDir);
            IndexSearcher searcher = new IndexSearcher(indexReader);
            TaxonomyReader taxoReader = new DirectoryTaxonomyReader(this.taxoDir);

            FacetsCollector fc = new FacetsCollector();

            FacetsCollector.search(searcher, new MatchAllDocsQuery(), 10, fc);//收集命中结果

            List<FacetResult> results = new ArrayList<FacetResult>();

            Facets facets = new FastTaxonomyFacetCounts(taxoReader,this.config,fc);//建立分组
            results.add(facets.getTopChildren(10, "Author", new String[0]));//向结果集中添加搜索结果
            results.add(facets.getTopChildren(10, "Publish Date", new String[0]));//只选取年份
            indexReader.close();
            return results;
        }

        private List<FacetResult> facetsOnly() throws IOException{
            DirectoryReader indexReader = DirectoryReader.open(this.indexDir);
            IndexSearcher searcher = new IndexSearcher(indexReader);
            TaxonomyReader taxoReader = new DirectoryTaxonomyReader(this.taxoDir);

            FacetsCollector fc = new FacetsCollector();//搜索结果收集器

            searcher.search(new MatchAllDocsQuery(),null, fc);//没有使用facet收集器

            List<FacetResult> results = new ArrayList<FacetResult>();

            Facets facets = new FastTaxonomyFacetCounts(taxoReader,this.config,fc);
            results.add(facets.getTopChildren(10, "Author"));
            results.add(facets.getTopChildren(10, "Publish Date"));//
            indexReader.close();
            return results;
        }

        private FacetResult drillDown() throws IOException {  
            DirectoryReader indexReader = DirectoryReader.open(this.indexDir);  
            IndexSearcher searcher = new IndexSearcher(indexReader);  
            TaxonomyReader taxoReader = new DirectoryTaxonomyReader(this.taxoDir); 

            DrillDownQuery q = new DrillDownQuery(this.config);// A Query for drill-down over facet categories 
            q.add("Publish Date", new String[] { "2010" }); //新建查询

            FacetsCollector fc = new FacetsCollector();  
            FacetsCollector.search(searcher, q, 10, fc);  
            Facets facets = new FastTaxonomyFacetCounts(taxoReader, this.config, fc);  
            FacetResult result = facets.getTopChildren(10, "Author", new String[0]); //只选取Author域的内容
            //FacetResult result = facets.getTopChildren(10, "Author", new String[0]);
            indexReader.close();  
            taxoReader.close();  
            return result;  
            }  

         private List<FacetResult> drillSideways() throws IOException {  
             DirectoryReader indexReader = DirectoryReader.open(this.indexDir);  
             IndexSearcher searcher = new IndexSearcher(indexReader);  
             TaxonomyReader taxoReader = new DirectoryTaxonomyReader(this.taxoDir);  

             DrillDownQuery q = new DrillDownQuery(this.config);  

             q.add("Publish Date", new String[] { "2010" });  

             DrillSideways ds = new DrillSideways(searcher, this.config, taxoReader);
             //Computes drill down and sideways counts for the provided DrillDownQuery  
             DrillSideways.DrillSidewaysResult result = ds.search(q, 10);  
             //Use one of the static search methods to do the search, and then get 
             //the hits and facet results from the returned DrillSideways.DrillSidewaysResult
             List<FacetResult> facets = result.facets.getAllDims(10);  
             indexReader.close();  
             taxoReader.close();  
             return facets;  
             }  

         public List<FacetResult> runFacetOnly() throws IOException {  
             index();  
             return facetsOnly();  
             }  
         public List<FacetResult> runSearch() throws IOException {  
             index();  
             return facetsWithSearch();  
             }  

         public FacetResult runDrillDown() throws IOException {  
             index();  
             return drillDown();  
             }  

         public List<FacetResult> runDrillSideways() throws IOException {  
             index();  
             return drillSideways();  
             }  

         public static void main(String[] args) throws Exception {  
             SimpleFacetsExample example = new SimpleFacetsExample();        
                     // two  
             System.out.println("Facet counting example (combined facets and search):");  
             System.out.println("-----------------------");  
             List<FacetResult> results = example.runSearch();  
             System.out.println("Author: " + results.get(0));  
             System.out.println("Publish Date: " + results.get(1));  

             // one  
             System.out.println("Facet counting example(only):");  
             System.out.println("-----------------------");  

             List<FacetResult> results1 = example.runFacetOnly();  
             System.out.println("Author: " + results1.get(0));  
             System.out.println("Publish Date: " + results1.get(1));  




                     // three  
             System.out.println("Facet drill-down example (Publish Date/2010):");  
             System.out.println("---------------------------------------------");  
             System.out.println("Author: " + example.runDrillDown());  

                     // four  
             System.out.println("Facet drill-sideways example (Publish Date/2010):");  
             System.out.println("---------------------------------------------");  
             for (FacetResult result : example.runDrillSideways()) {  
                 System.out.println(result);  
             }  
             }  

}

可以看到，Facets的构是由

Facets facets = new FastTaxonomyFacetCounts(taxoReader,this.config,fc);

FastTaxonomyFacetCounts的构造函数完成的，而FastTaxonomyFacetCounts的构造则需要Facets模块专门的FacetConfig以及FacetCollector,，然后，facet模块中还提供了DrilldownQuery来在facet之上钻取数据，辅助DrilldownQuery的有一个继承自Object的类DrillSideways，该类直接由reader,FacetConfig还有FacetCollector构建，并且调用方法DrillSidewaysResult（）来获取facet结果（统计某一组域的结果的总数）。